Patent Application
20180322254
The invention relates generally to a network system and methods of using the same for receiving and transmitting streaming imagery data, including medical images, waveforms, audio and haptic signals, biomedical and clinical documents, both live and asynchronously, allowing operators to concurrently curate, annotate, tag, encapsulate and save that imagery data, together with those annotations and searchable metadata tags in single file format structures. The invention acquires streaming imagery data through network-connected imagery-enabled devices, and allows a variety of cognitive collaborants, singly or together, to concurrently communicate, collaborate, consult and instruct, generally by curating, annotating and tagging, telestrating, sketching image overlays on streaming imagery data, and saving those images together with collaborated annotations and metadata, as streaming augmented intelligence for rapid adaptive learning and specialist skills acquisition with multimodal cognitive instruction and informatics-enriched value chain knowledge exchange.
As used herein, “cognitive collaborant” refers to one or more cognitive collaborators, human or non-human, including heterogeneous networked teams of persons, machines, devices, neural networks, robots and algorithms.
The invention enables multichannel multiplexed communications, collaboration, consultation and instruction with streaming imagery data by heterogeneous networked teams of cognitive collaborants, including persons, machines, devices, neural networks, robots and algorithms. The invention enables both synchronous and asynchronous multimodal cognitive communications, collaboration, consultation and instruction during various stages of medical disease management, including detection, diagnosis, prognosis, treatment, measurement, monitoring and reporting.
The invention enables pluribus network encoding with multichannel multiplexed steaming imagery data from signals, sensors and devices, including packets, waveforms and streams, along with space shifting, time shifting and format shifting media synchronization. The invention enables heterogeneous networked teams of cognitive collaborants to recursively curate, annotate and tag, encapsulate, save and share multichannel multiplexed imagery data streams, including multisensory data stream visualization and bi-directional value chain knowledge exchange, with streaming imagery data from heterogeneous spatial and temporal sources, locations, modalities and scales. The invention acquires both live stream and archived medical imagery data from network-connected medical devices, cameras, signals and sensors. The network system also acquires multiomic data—phenotypic, genomic and metabolomic, as well as pathomic, radiomic, radiopathomic and radiogenomic—from structured reports and clinical documents, as well as biometric maps, movies, data stream visualizations, hapmaps and heat maps. The network system also acquires packetized clinical informatics from imagery data repositories, from clinical workstations and mobile medical devices, as well as from wearable computing devices, signals and sensors.
The invention enables networked teams to interactively communicate, concurrently collaborate and bi-directionally exchange multichannel multiplexed imagery data streams, singly or together, in real time or asynchronously, generally by curating, annotating and tagging imagery information objects. The invention encapsulates and saves collaborated imagery data streams, together with collaborated clinical annotations, imaging metadata, as well as semantic metadata and annotations, and privacy protected metadata identifying personal health information [PHI], in standard known file formats as clinical cognitive vismemes—encapsulated packets, waveforms and streams. Clinical cognitive vismemes preserve packetized imagery information objects, clinical annotations and metadata tags in native file format structures, including PDF, MPEG, JPEG, XML, XMPP, TIFF, RDF, RDF/XML, QR, SVG and DAE, as well as DICOM. When clinical cognitive vismemes are encapsulated and saved in formats compliant with standards for digital communications in medicine [DICOM], they can also be referred to as medical dicom vismemes.
Clinical cognitive vismemes allow for recursive cognitive enrichment through recursive curation, annotation, tagging, encapsulation and saving, together with value chain knowledge exchange. Value chain knowledge exchange includes knowledge acquisition and creation, knowledge visualization and sharing, knowledge replication and integration, knowledge protection and destruction, as well as outcomes performance evaluation and outcomes-driven innovation with accelerated value chain knowledge exchange.
The invention also enables informatics-enriched innovation and value chain knowledge exchange with multimodal cognitive communications and multisensory data stream visualization. Multimodal cognitive communications, collaboration, consultation and instruction includes multisensory [sight-sound-touch] digital data exchange with vision, audition and sensation, including semiotics, semantics and somesthetics [haptics].
The invention enables live stream multicasting of N-way multi-party collaborations, including multisensory data stream visualization and bi-directional knowledge exchange, with multichannel multiplexed imagery data streams, and concurrent transmission of secure, encrypted clinical cognitive vismemes across collaborative file sharing data networks for informatics-enabled learning, specialist skills acquisition and accelerated knowledge exchange. Principal areas of clinical application include cognitive enterprise imaging with streaming imagery informatics, collaborative precision medicine with multiomic data analytics, informatics-enabled imagery guided intervention, including robotic-assisted surgery, along with newly-emerging disciplines for machine learning with medical imaging, including deep learning, transfer learning, reinforcement learning and convolutional neural networks, precision guided biomedical nanorobotics and precision targeted theranostic nanomedicine.
The novelty of the present invention enables multiparty networked cognitive communications, collaboration, consultation and instruction with streaming imagery data by integrating videoconferencing systems technology with emerging applications and techniques for machine learning in medicine.
Digital clinical data, captured and stored on electronic medical records by hospitals and clinics, along with ever growing volumes of medical imaging data, have sparked growing interest and applications of machine learning in medicine.
In recent years there has been a proliferation of AI tools and resources available in medicine, especially with ever increasing computing power and a growing acceptance of cloud computing by hospitals and clinicians. Imaging analysis and clinical decision support are two particularly popular applications of machine learning in medicine, with tools that support diagnosis, treatment, care coordination and remote monitoring.
Already used in areas such as radiology, pathology, genomic medicine, cardiology, outpatient services, and intensive care, AI will continue to have escalating impact in medicine. There is much promise in the utilization of AI methodologies such as deep learning for automated and/or augmented biomedical image interpretation in radiology, pathology, dermatology, ophthalmology and cardiology in the near future.
Examples abound of increasing application of machine learning in medicine. Some hospitals have developed AI-backed decision support platforms with cloud computing for the diagnosis and treatment of pediatric brain diseases. They have complied a reference library of normal pediatric MRI brain scans coupled with deep learning. This can be particularly helpful for diagnosing pediatric brain disorders that might otherwise be misinterpreted as normal, and normal brain development that can be misdiagnosed as abnormal changes, both of which lead to misdiagnoses and inappropriate treatment.
Another example of machine learning for medicine involve differentiating diagnosis for stage I breast cancer with use of computer-aided diagnosis that enables joint analysis of functional genomic information and image from pathological images (pathogenomics). The biomedical imaging informatics framework consisted of image extraction, feature combination, and classification.
And recently, algorithms based on deep convolutional neural network to detect diabetic retinopathy in retinal fundus photographs. That study showed that algorithms can be as good as board-certified ophthalmologists in making diagnoses with high specificity and sensitivity.
Precision medicine with its complexity and enormity of data to be analyzed is particularly well suited for the portfolio of AI methodologies such as deep learning as similar patients can be identified and assessed. In genomic diagnostics, clinicians are often frustrated by the tedious nature of searching for genotype-phenotype interrelationships among syndromes, especially for extremely rare diseases. Now, geneticists are able to use a visual diagnostic decision support system that employs machine learning algorithms and digital imaging processing techniques in a hybrid approach for automated diagnosis in medical genetics.
In addition, there are many potential applications of deep learning for large datasets in pharmaceutical research (such as physicochemical property prediction, formulation prediction, and properties such as absorption, distribution, metabolism, excretion, toxicity, and even target prediction. An essential part of the precision medicine paradigm is individualized therapy based on genotype-phenotype coupling and pharmacogenomic profiles.
Surgical robotics have advanced to include 3D visualization and informatics-enriched imagery guided interventions.
Machine learning algorithms have also been applied to large-scale wearable sensor data in neurological disorders such as Parkinson's disease to significantly improve both clinical diagnosis and management. This sensor-based, quantitative, objective, and easy-to-use system for assessing Parkinson's disease has potential to replace traditional qualitative and subjective ratings by human interpretation.
An essential part of digital medicine and wearable devices is the data mining of the incoming data for anomaly detection, prediction, and diagnosis/decision making. The data mining process for wearable data includes a feature extraction/selection process for modeling/learning to yield detection, prediction, and decision making for the clinician. Expert knowledge and metadata can influence modeling and learning.
AI techniques such as artificial neural networks, support vector machines, classification tree and ensemble methods such as random forest are able to be applied to molecular imaging modalities in clinical diseases promising application to clinical diagnosis. Machine learning include supervised methodologies such as neural networks, support vector machines, naïve Bayesian classifiers, and hidden Markov models, as well as semi-supervised techniques that can be used with less labeled data.
Three types of learning: deep, reinforcement, and one-shot learning will figure prominently in the future of AI in medicine as these methodologies can potentially accommodate the nuances and complexities of medicine.
Deep learning with all its capabilities will be used for much of medical Big Data. The multiple layers of neural nets can be assigned to the many phenotypic as well as genomic expressions of conditions such as clinical measurements, biomarkers, imaging data, genomic information and disease subtypes. In addition, reinforcement learning is ideally designed for the many decision making aspects of medicine since it accommodates for recognition of complex patterns, long-term planning, and decision-making. Finally, there is also transfer learning that occurs when a network that is trained for one task is then used to configure the network for another task. The relatively new one-shot learning can bring a special dimension to unique cases in medicine as it will not require the usual large dimensionality of data that the previous types of learning will need (e.g., unsupervised, semi-supervised, and one-shot learning)
Precision medicine at its highest level may require a disruptive computational platform for new biomedical knowledge discovery, a scalable computational framework leverages a hypergraph-based data model and query language that may be suited for representing complex multi-lateral, multi-scalar, and multi-dimensional relationships. A hypergraph-like store of public knowledge is coupled with an individual's genomic and other patient information (such as imaging data) to drive a personalized genome-based knowledge store for clinical translation and discovery. Patients of very similar genomic and clinical elements can be discovered and matched for diagnostic and therapeutic strategies.
Cloud computing and storage will be vital to facilitate the panoply of AI techniques for multi-institutional collaborations that will be essential for the future of AI in biomedicine and healthcare. The internet of medical things and everything (IoMT) will also provide the critical data sources for medicine in the form of wearable and monitoring devices from both hospital and home.
Best practice in the near future will involve the use of data and analytics to answer the clinical questions (intelligence-based medicine) rather than current practice of solely relying on published reports (evidence-based medicine).
The future of artificial intelligence appears promising, based on rapid improvement and deployment of ever more capable biomedical informatics infrastructure, including advanced computer technology and cloud storage, along with rapid development and evolution of artificial intelligence techniques such as graph databases, computer vision, natural language processing, internet of things and everything, neuromorphic computing, and deep learning.
There is a compelling need for technologies to improve diagnostics and therapeutics to deliver value-based care in the present medical and health care. The convergence of Big Data, improved algorithms, computational power, and cloud storage has started to yield robust machine learning projects and results in biomedicine and healthcare, but the most important aspect of advances in AI in healthcare will need to be the sharing of data and collaboration amongst all stakeholders.
AI can be ubiquitous in the health care arena and will help discover new knowledge from all sources of data and information. The most productive strategy will need to involve an intimate human-machine synergy with continual clinician-data scientist collaboration. Machine learning in medicine may become a key enabler of new clinical knowledge and augmented medical intelligence.
Collaborative Clinical Workflows with Enterprise Imaging
The HIMSS-SIIM Collaborative Workgroup has defined Enterprise Imaging as:
An enterprise imaging (EI) platform typically provides the infrastructure, modalities, devices, and integration points on which strategies can be based. A standards-based DICOM and non-DICOM clinical image and video storage repository is central to the EI platform. This central repository may be a vendor neutral archive or, if it meets defined enterprise-wide requirements, an existing PACS archive. It includes an index of the image and meta-information content in the archive.
Medical imaging archives increasingly are modality agnostic, modality vendor agnostic, specialty and service line agnostic, and viewer agnostic. Standards-based interfaces and communications, including DICOM, HL7, and standards-based Web Services, connect, enable, and support image acquisition workflows across modalities and departments. Image acquisition devices that support these standards may store their images, with meta-information, into the VNA. Acquisition devices that are supported include departmental DICOM imaging modalities, point-of-care acquisition modalities, handheld device photo or video apps, digital capture systems in procedure rooms, image exchange gateways, and software designed to import content saved on a disk or received by referring or patient portals.
Clinical content and multimedia content span four broad categories medical workflows with Enterprise Imaging: diagnostic imaging, procedural imaging, evidence imaging, and image-based clinical reports, as depicted in
Medical workflows across many departments capture and create a variety of types of “multimedia” information that is important to preserve, correlate with the images, and make accessible via the medical record. This multimedia content includes waveforms, audio or video clips, as well as other forms of graphical content that summarize imaging results with the results from other medical procedures and tests. Examples of this are present in many specialties including Ophthalmology, Cardiology Neurology, OB, and GI.Graphical “report-style” results from various medical departments are increasingly being created and saved as PDF objects. These can include embedded images that show key findings, graphical diagrams that show the area of interest, or other measurement or test result information that correlates with the images.
Another example of related multimedia content includes time-based waveforms such as those produced by ECG or EEG devices. These may be treated as documents or image-like objects. Waveforms may be recorded and stored in a raw or processed form that requires an application to display them, or in some human-readable rendered form (like a PDF or screenshot). Like images, waveforms too can be classified as both evidence and diagnostic. Waveforms are the graphical representation of discrete data points but may be used as the sole basis of interpretation when other tools for analysis of discrete data points are not available or routinely incorporated within the interpretation protocol.
Most types of multimedia content, including waveforms, PDF reports, MPEG video clips, and JPEG photos, can be DICOM wrapped and stored as DICOM objects or they can be treated as a native document type (e.g., PDF, JPEG, MPEG, etc.) and saved in system that can manage them as native objects. What is important is to consider how this information will be managed, correlated, accessed, and viewed by physicians and patients. Related images and multimedia content should be easily discoverable and shown together in a natural way.
DICOM provides support for encoding both generic identification and modality and specialty-specific acquisition context for all enterprise imaging modalities. DICOM-like metadata can also be added to other image file formats like JPEG or TIFF, though this is rarely done for medical metadata (but is common for photographic metadata., such as in the Exchangeable Image File Format (EXIT) extension to REG). Other alternatives include encapsulating the image in a different standard format, such as HL7 Clinical Document Architecture (CDA), as is defined by the IHE Scanned Document (XDS-SD) profile, so that the metadata remains directly associated with the image. Strictly speaking, the XDS-SD profile defines a limited set of media types that may be encapsulated, but the approach can be generalized.
The invention described herein supports both approaches to encapsulating and saving medical metadata with their associated medical imagery.
Video Collaboration with Medical Imaging
This invention relates to a videoconferencing system for ‘live’, e.g., real time, near real time or minimally latent, viewing of streaming medical imagery, and more particularly, to a network system and methods of using said medical imaging videoconferencing system with multiple input operators or participant cognitive collaborants viewing each other's inputs collaboratively and concurrently.
In past systems the computer arrangement for video conferencing systems can be summarized as a plurality of users systems connected to each other, each being adapted to display a work area on a display screen or connected through a computer network. Collaboration of work is done on each system by use of a management table for registered node identification codes given for each system user. That is, every computer system, or one system, requires storage of collaboration user identifier in at least one of the user's computer system. These novel systems and methods of multimodal cognitive communications, collaboration, consultation and instruction for use with medical imagery have improved upon the past art by allowing modular and scalable network clusters of gateway streamer servers that enable dynamic control allowing for faster and more efficient performance, as well as enabling for multiparty cognitive collaboration with medical images in Digital Imaging and Communications in Medicine, hereinafter referred to as DICOM, environment.
The DICOM Standard pertains to the field of medical informatics. The DICOM Standard is well known in the arts and facilitates interoperability of medical imaging equipment by specifying a set of protocols to be followed by devices claiming conformance to the standard. The DICOM Standard outlines syntax and semantic of commands and associated information which can be exchanged using these protocols. For media communication, a set of media storage services to be followed by devices claiming conformance to the DICOM Standard, as well as file format and medical dictionary structure to facilitate access to the images and related information stored on interchange media. DICOM data file format is data formatted in groups of information, known as Data Sets. The DICOM Standard provides a means to encapsulate in a single file format structure the Data Set related to a DICOM information object. The DICOM Standard requires a single file format structure, as the DICOM Standard specifies that each DICOM file contain both File Meta Information and a properly formatted Data Set (as specified in DICOM Standard 3.10). The DICOM Standard further specifies that the byte stream of the DICOM Data Set be placed into the file after the DICOM File Meta Information (as specified in PS 3.10 DICOM Part 10: Media Storage and File format for Media Interchange).
The DICOM Standard specifies the rules for encapsulating DICOM Data Sets in the requisite DICOM File format. The DICOM Standard requires that a file meta information header be present in every DICOM file, and that the file meta information includes identifying information of the Data Set (PS 3.7-1). The DICOM Standard requires that the Data Set conform to the service-object pair (SOP) Class specified in the file meta information. “The DICOM File format provides a means to encapsulate a File the Data Set representing a SOP Instance relating to a DICOM Information Object.” The DICOM Standard provides for the encapsulation of waveform data (PS 3.5 Part 5: Data Structures and Encoding), and for the encapsulation of structured reports (Supplement 114: DICOM Encapsulation of Clinical Document Architecture Documents) within imagery bit streams to facilitate the interchange of information between digital imaging computer systems in medical environments.
The DICOM File Meta Information includes identifying information on the encapsulated DICOM Data Set. The DICOM Standard requires that a file header of identifying information be present in every DICOM file. The DICOM file header consisting of a 128 byte File preamble, followed by a 4 byte DICOM prefix, followed by the File Meta Elements. This means, for example, that a DICOM file of a chest x-ray image actually contains the patient identification within the file, so that the image can never be separated from patient information by mistake. A DICOM file contains both the image and a large amount of patient information about whom, where, and how the image was acquired, known in the arts as patient metadata.
However, DICOM files often contain little information about the content of the imagery or meaning of the imagery pixels, the encapsulated waveform data used for audio clinical notes, or the encapsulated structured reports used for clinical documents, all of which are used for clinical detection, diagnosis and treatment of disease. This network system improves upon and applies in a collaborative environment which provides for capture, retrieval and concurrent viewing of both live and archived medical imagery streams for communication, collaboration and consultation with one or more sources of streaming imagery data by one or more users, also known as participant cognitive collaborants. Collaborated medical imagery streams comprise one or more sources of streaming imagery data, including DICOM imagery files. As used herein, DICOM imagery files include modality information objects, (e.g. streaming video), waveform information objects (e.g. voice audio, echocardiogram), and structured report document information objects (e.g. clinical documents), as specified in PS 3.3 Part 3: Information Object Definitions of the DICOM Standard.
Medical imagery streams include DICOM imagery files. This network system allows for each user to collaborate simultaneously with all users viewing every other users' work product, as the work product is being created, all coincident with one or more streams of streaming imagery data wherein each server manages streams of medical imagery together with participant cognitive collaborant input illustrations for use with DICOM imagery files. The network system provides live video and audio communication, as well as a method of viewing, recording and transmitting streaming imagery data, which include DICOM imagery files, in DICOM format, which requires a single file format structure. Streaming imagery data includes both live and archived imagery data. As used herein, multi-channel streaming imagery data is defined as a collection of one or more sources of streaming imagery data each of which comprise at least one image frame that defines a time progression of output from various sources, which include video, encapsulated waveform data, and encapsulated structured reports.
The network system provides multi-channel multiplexed capability for capture, retrieval and concurrent viewing of both live and archived medical imagery streams for communications, collaboration, consultation and instruction with one or more sources of streaming imagery data by participant cognitive collaborants. Participant cognitive collaborant input illustrations as defined herein include, but are not limited to telestrations, drawings, sketches, text annotations, including letter character text and numeric character text, image annotations, wave form annotations, voice annotations, video annotations, augmented reality imagery annotations, 3D/4D imagery annotations, outcomes annotations, costs annotations, resource consumption/utilization annotations, haptic annotations, patient metadata, imagery metadata, semantic metadata and annotations, appended patient metadata, appended imagery metadata and appended semantic metadata and annotations. The network system appends participant cognitive collaborant input illustrations to streaming imagery data, and encapsulates and saves those input illustrations, together with streaming imagery data, and relevant imagery metadata and semantic metadata and annotations, including appended imagery metadata and appended semantic metadata and annotations, from the collaboration session in single file format structures, known as collaborated imagery files. The ‘single file encapsulate and save’ functionality of the network system encapsulates and saves collaborated imagery files in single file format structures, as may be required or allowed by standards for clinical documentation or medical records storage, including those as specified in the DICOM Standard (e.g. as DICOM files).
The network system appends metadata tags to participant cognitive collaborant input illustrations and encapsulates and saves those tagged input illustrations together with the Data Set from the streaming imagery data and relevant metadata information from the metadata header in single file format structures for use within a DICOM imagery environment, including those as specified in the DICOM Standard. The network system appends metadata tags to alpha-numeric text annotations, image annotations, wave form annotations, voice annotations, video annotations, augmented reality imagery annotations, 3D/4D imagery annotations, outcomes annotations, costs annotations, resource consumption/utilization annotations, haptic annotations and clinical documents and encapsulates those alpha-numeric text annotations, image annotations, wave form annotations, voice annotations, video annotations, augmented reality imagery annotations, 3D/4D imagery annotations, outcomes annotations, costs annotations, resource consumption/utilization annotations, haptic annotations and clinical documents and saves those as DICOM files. The network system can also append annotation files encapsulated as DICOM files to the Data Set for streaming imagery data, and encapsulate them together with relevant metadata information from the metadata header for streaming imagery data, and save in single file format structures as collaborated imagery files (CIF).
Collaborated imagery files, also known as CIFs, conform to the DICOM Standard and can be stored, archived, queried, and retrieved as DICOM files. CIFs can be stored locally in media libraries and later retrieved for subsequent use in collaboration sessions. CIFs conform to the DICOM Standard [3.10] and can be encrypted and/or transmitted over networks for remote viewing, communication and collaboration. CIFs conform to specifications of the DICOM Standard for secure encapsulation of DICOM objects in a clinical document architecture (CDA). As such CIFs can be stored as in archives conforming to health level seven (HL7), integrating the healthcare enterprise (IHE), cross-enterprise document sharing (XDS), cross-enterprise document sharing for imaging (XDS-I), Extensible Markup Language (XML), in Tagged Image file format (TIFF), as well as in RDF triples and RDF/XML for metadata model specification.
CIF's can also contain encapsulated and saved haptic imagery and annotations in COLLADA-compliant dae files. COLLADA (collaborative design activity) is an interchange file format for interactive 3D applications that has been adopted by ISO as a publicly available specification, ISO/PAS 17506. COLLADA defines an open standard XML schema for exchanging digital assets among various graphics software applications that might otherwise store their assets in incompatible file formats. COLLADA documents that describe digital assets are XML files, usually identified with a .dae (digital asset exchange) filename extension.
CIFs conform to specifications of the DICOM Standard for encapsulation of audio with imagery data sets. CIFs conform to specifications to the DICOM Standard for DICOM structured reporting. CIFs can be viewed as stand-alone medical imagery, or embedded into other CIFs as video, audio and haptic annotations. The network system can create collaborated imagery studies, also known as CIS's, which include one or more collaborated imagery files, encapsulated and saved in single file format structures, as may be required or allowed by standards for clinical documentation or medical records storage, including those as specified in the DICOM Standard format. Collaborated Imagery Studies, also known as ‘Clini-DOCx’ are visual story boards can be used for capture, display, file exchange, publication and distribution of collections of clinical cognitive vismemes.
The DICOM Standard defines the characteristics of a medical study performed on a patient as, “a collection of one or more series of medical images, presentation states, SR documents, overlays and/or curves that are logically related for the purpose of diagnosing a patient. Each study is associated with exactly one patient” (PS 3.3 A.1.2.2 STUDY IE). Streaming imagery data can include both collaborated imagery files and collaborated imagery studies. Both CIFs and Clini-DOCx can be incorporated into medical image streams of live or archived streaming imagery data for use during synchronous or asynchronous collaboration sessions.
The traditional way of capturing an image from a medical imaging device commonly called a modality, generally consisted of an operator or technician first conducting a scan. Then, using the modality to save the image, in still or motion video format, into the modality memory or into a main image storage database. The next step in the process typically involved downloading the image into a hospital database, known in the arts as a Picture Archiving and Communications System, hereinafter referred to as PACS or PACS server. PACS is a medical imaging technology which provides economical storage of, and convenient access to, images from multiple modalities (source machine types). Electronic images, including patient information known in the arts as patient metadata, are transmitted digitally to and from PACS, eliminating the need to manually file, retrieve or transport film jackets. The universal form of PACS image file storage and transfer is the DICOM Standard, and is well known in the arts. PACS can be further defined by a storage and management system for medical images.
In the medical field, images such as x-rays, MRI's and CAT scans typically require a greater amount of storage than other images in other industries. A clinician would access the PACS system to retrieve the image, view and review the image, and conceivably develop a diagnosis based on the information from the image. This system imagery is viewed by a user and diagnosis made without image delay and the user accomplishes all these tasks live. “Live” referring to events simulated by a computer at the same speed that they would normally occur in real life. In graphics animation, for example, a live program (such as this inventor's system) would display objects moving across the display at the same time they would actually move, or in the case of this invention, a cognitive collaborant views the image live and collaborates from cognitive collaborant to cognitive collaborant with no perceivable delay to any of them.
The inventor has developed a novel and simple network system and methods of using the same, to allow a group of cognitive collaborants to concurrently collaborate on a computer system, with each participant cognitive collaborant viewing each other's telestrations, drawings, and annotations and saving them together with streaming imagery data, annotations and relevant imagery metadata, including appended imagery metadata and semantic metadata and annotations, and saving them together in single file format structures as may be required or allowed by standards for clinical documentation or biomedical records storage, including those as specified in DICOM, C-CDA and FHIR Standards for interoperable health information exchange.
A network system and methods for using the same for concurrent collaboration between users, collaborating by a variety of input illustrations, which include video, audio, telestrations, drawings and annotations, as well as collaborating on medical images that are typically accessed on a storage server database, imaging archives, or continuous streaming video.
The invention relates generally to a multimedia collaborative conferencing system and methods of using the same for generating input illustrations, which include telestrations, drawings and annotations on medical images concurrently with other users and saving participant cognitive collaborant input illustrations with streaming imagery data, annotations and relevant imagery metadata, including appended imagery metadata in single file format structures, including those as specified in the DICOM Standard.Applicant's network system is known as the TIMS Clinical Network System. It is comprised of three essential components: one called TIMS Clini-Pod Network Servers (CNS); another called TIMS Clini-Ports; and a third called TIMS Clini-Docks, as depicted in
TIMS Clini-Docks include a medical image acquisition system adapted for receiving and transmitting medical images, constructed from, a computer having communications capability adapted for acquisition and transmission of a plurality of medical imaging and video signals. Wherein the medical image and video signals are acquired at the medical device's native resolutions, transmitting the signals at their native resolutions and native frame rates to a receiving device, receiving the medical imaging video signals in analog or digital form, and if required, compressing and scaling the signal, converting the signal to digital form for transmission, and transmitting the digital signals using secure encryption protocols_to a display device. TIMS Clini-Docks are capable of concurrently acquiring signals from a plurality of medical imaging systems, as depicted in
TIMS Clini-Docks can also receive the video image signal from a plurality of video sources, including but not limited to, S-video, composite color and monochrome, component red blue green video (RGB, three additive primary colors), Digital Visual Interface (DVI), any video transport protocol including digital and analog protocols, high definition multimedia interface (HDMI, compact audio video interface uncompressed digital data), serial digital interface (SDI), and DICOM video in their native, enhanced or reduced resolutions or their native, enhanced or reduced frame rates. The component, known in this invention as TIMS Clini-Pod Network Servers (CNS), manage communications between all acquisition systems (TIMS Clini-Docks), between all TIMS Clini-Ports, the computer workstations used by cognitive collaborants during collaboration sessions, between hospital servers, located on site or remotely, that store hospital images, and hospital networks in both local area and wide area configurations.
TIMS Clini-Pod Network Servers (CNS) manage both live and archived streaming imagery data acquired from TIMS Clini-Docks, and archived imagery, including collaborated imagery files, retrieved in predetermined digital single file format structures, including those as specified in DICOM Standard, and stored locally in media libraries on participant cognitive collaborants computer storage devices, in image data repositories on tele-visual imagery informatics management system servers, in image data repositories on cloud storage devices and locations, in image data repositories on picture archiving and communications system repositories, on other image data repositories compliant with standards for digital imaging and communications in medicine, or on any other data repository that allows streaming imagery data, annotations and metadata to be combined in single file format structures, including clinical data repositories, personalized clinical knowledge repositories, clinical cognitive vismeme vaults and metadata repositories.
A participant or user computer can be defined as typically made of several components such as a main circuit board assembly having a central processing unit, memory storage to store programs and files, other storage devices such as hard drives, and portable memory storage, a power supply, a sound and video circuit board assembly, a display, and an input device such as a keyboard, mouse, stylus pen and the like allowing control of the computer graphics user interface display, where any two or more of such components may be physically integrated or may be separate. In one depiction, a remote location communicates with the networked computer, for the purpose of collaborating and conferencing with medical streaming imagery data.
TIMS Servers (CNS) manage the master control functionality of the TIMS Clinical Network System. This functionality is achieved via the connection of TIMS Servers (CNS) to TIMS Clini-Docks and allows multiple users in multiple locations to view live all telestrations, and annotations from each of the users during collaboration sessions, as depicted in
TIMS Clini-Pod Network Servers (CNS) are typically deployed in several configurations: Clini-Pod or pairs, typically 1-2 Clini-Pods (hub-and-spoke or peer-to-peer); Clini-Pod Quads, or teams [typically 2-4 Clini-Pods); Clini-Pod Squads, (typically four Quads, or 16 Pods) and Clini-Pod Hives [4 Clini-Pod Squads]. Local CNS network servers connect individual cognitive collaborants, also known as pod team members to devices in their Clini-Pod, as depicted in
TIMS Clini-Port software applications allow participant cognitive collaborants to add other sources of streaming imagery data by selecting the “add+” channel selection tab, and viewed on the channel tabs of the multi stream viewer as shown in
In one embodiment, the connection of TIMS Clini-Pod Network Servers (CNS) to TIMS Clini-Docks allows TIMS Clini-Ports to customize preferences for capture, retrieval, and viewing of streaming imagery data while the patient is still on the examination table. TIMS Clini-Ports can have direct access and control of the streaming imagery data and maintain the native resolution and frame rate output from the medical modality. If desired, TIMS Clini-Ports can adjust the native resolution, frame rate, and compression of the streaming imagery data specific to the user's preferences. In addition, TIMS Clini-Ports are able to live instruct clinicians who are controlling streaming imagery data at their respective modality sources, and view the results of those instructions to ensure that imagery acquired is consistent with user preferences, as depicted in
Without access to master control of TIMS Clini-Docks by TIMS Clini-Pod Network Servers (CNS), imagery viewed by a remote client using another invention is limited to the quality of the view and capture settings specified by others, which may be different than those desired or required by the remote client. TIMS Clini-Docks are multichannel streamer stacks that allow live capture and archived retrieval for tele-visual communications with: (1) streaming video; (2) medical imagery modalities and waveforms; (3) electronic medical records; and (4) clinical and multiomic maps and biometric data stream visualizations.
As used herein, “streaming medical imagery” includes all information objects described in the DICOM Standard, including images, video, modality imaging and waveforms—audio, visual and haptic wave forms and files, medical records and clinical documents, multiomic-phenotypic, genomic, metabolomic, pathomic, radiomic, radiopathomic and radiogenomic, pathomic, radiomic, radiopathomic and radiogenomic—maps and clinical data sets, including those as described in the Institute of Medicine's Towards Precision Medicine—A New Taxonomy of Disease; along with biometric data stream visualizations from connected medical devices, signals and sensors used for local and remote patient monitoring.
In one embodiment TIMS Clini-Docks can be deployed in four (4) dual channel streamer stacks to accommodate both live and archived streaming imagery data from these four principal modalities for tele-visual communications and collaboration with imagery informatics. Clini-Dock streamer Channel (1) is typically reserved for video communications and conferencing among team members and other cognitive collaborants. Channel (2) normally designated for electronic medical records and patient monitoring; Channel (3) for medical imaging modalities and wave forms. Channel (4) for data mapping and interactive biometric data stream visualizations, including virtual reality and augmented reality displays. The TIMS Clini-Port typically has one or more multi-channel monitors for connected devices, which can be situated locally, within the Clini-Pod, or at remote locations, including other Clini-Pods.
TIMS Clini-Docks, due to its novel capabilities, can acquire analog or digital video signals, standard or non-standard video resolutions, medical or non-medical imagery, live or archived imagery, and compressed or uncompressed imagery formats. TIMS Clini-Docks converts analog sources of streaming imagery data, as well as non-standard sources of streaming imagery data into digital imagery data sets for use by participant cognitive collaborants during collaboration sessions. TIMS Clini-Docks can also convert non DICOM digital imagery data sets, including non DICOM modality imaging (e.g. video), waveform data (e.g. voice, audio, haptic), and structured reports (DICOM-SR from PACS) and clinical documents (CCD, CCR from EHR medical records systems) into DICOM imagery streams for use by participant cognitive collaborants during collaboration sessions. The TIMS Clini-Dock stack depicted in
TIMS Clini-Docks are connected directly to multiple sources of streaming imagery data, as depicted in
TIMS Clini-Pod Network Servers (CNS) keep track of all TIMS Clini-Docks that have image streams available and displays a list of image streams available TIMS Clini-Ports, as depicted in
A DICOM study is defined as a collection of one or more medical images and patient data combined in single file format structures, including those as specified in the DICOM Standard. DICOM Modality Worklist is defined as a software utility that invokes DICOM query and retrieve functionality which enables imaging equipment (e.g. medical modalities) to query medical image stores, including but not limited to PACS, and obtains details of patient and scheduled examinations electronically, including patient demographics and study data, avoiding the need to type patient information multiple times, as depicted in
TIMS Clini-Pod Network Servers (CNS) also manage all the participant cognitive collaborant input illustrations, specifically, the entire participant cognitive collaborant input illustrations, sketches, drawings, telestrations and annotations. Participant cognitive collaborant input illustrations as previously defined herein include, but are not limited to telestrations, drawings, sketches, text annotations, including letter character text and numeric character text, image annotations, wave form annotations, voice annotations, video annotations, augmented reality imagery annotations, 3D/4D imagery annotations, outcomes annotations, costs annotations, resource consumption/utilization annotations, haptic annotations, imagery metadata and appended imagery metadata, as depicted in
TIMS Clini-Pod Network Servers (CNS) allow TIMS Clini-Ports to create collaborated imagery files synchronously or asynchronously. TIMS Clini-Pod Network Servers (CNS) use a process of local registration to identify the image frames needed for viewing on each of the participant cognitive collaborant computers, and sends to each of them only the image frames necessary for participation in a collaboration session. TIMS Clini-Pod Network Servers (CNS) enable each participant cognitive collaborant to use a scalable window so all input illustrations for each and every participant cognitive collaborant are dynamically ratio metric based on the underlying image aspect ratio of the respective participant cognitive collaborant computer. Therefore, all the input illustrations always point to the part of the window and image as originally intended, regardless of window size on the clients computer display. A central frame counter originating in the participant cognitive collaborant computer, which has play/pause control, issues frame synchronization commands to synchronize the image streams on all participant cognitive collaborants' computers. This method significantly reduces bandwidth requirements and improves responsiveness of system updates and imagery appends. Each client computer which has play/pause control also sends synchronizing commands whenever its displayed images are paused. This ensures that the same frame is available to all participating clients by broadcasting that pause frame number along with the pause command to all participating clients.
Client participants can receive video streams directly from TIMS Clini-Docks using a local area network. The invention can also detect if a user has low bandwidth, in transmission, or in reception, or in both and can compensate by only sending selected image frames to that user. For example, with low bandwidth TIMS Clini-Pod Network Servers (CNS) can send every third, fifth, or Nth frame of a collaborated imagery to clients so that client does not have any perceptible delay. Remote client participants using the internet must receive all imagery from TIMS Clini-Pod Network Servers (CNS) for secure transmission, rather than directly from local TIMS Clini-Docks, to ensure streaming imagery data is not transmitted over the internet without encryption.
TIMS Clini-Ports, also known as participant cognitive collaborants, can take several roles. Each participant cognitive collaborant can capture, retrieve and concurrently view both live and archived streaming imagery data of their own choosing, including medical imagery streams selected for the collaboration session; capture, retrieve and concurrently view both live and archived streaming imagery data streams selected by other participant cognitive collaborants, including medical imagery selected for the collaboration session; each participant cognitive collaborant can add multiple sources of streaming imagery data, also referred to as multiple channels, of both live and archived streaming imagery data for other participant cognitive collaborants to capture, retrieve and concurrently view; capture, retrieve and concurrently view multiple sources of both live and archived streaming imagery data, including medical imagery streams selected for a collaboration session; concurrently add input illustrations on both live and archived streaming imagery data; taking on any and all of the above roles dynamically, as depicted in
In addition, TIMS Clini-Port software applications are collaborative, interactive tools for synchronous or asynchronous media annotation, which can be used with medical files to enable participant cognitive collaborants to communicate, collaborate, consult and instruct with medical images for clinical review and discussions and deciding on relevant medical procedures.
This novel invention—combination streamer-splitter-server-router—network gateway servers—allows any of the TIMS Clini-Ports to host a collaboration session with any other TIMS Clini-Port, in various network configurations, including peer-to-peer, hub-and-spoke, mesh chord networks, as depicted in
All input illustrations added by participant cognitive collaborants are concurrently visible to all of the other participant cognitive collaborants. In addition, each participant cognitive collaborant can add input illustrations, which include telestrations, drawings, text annotations, image annotations, wave form annotations, voice annotations, video annotations, augmented reality imagery annotations, 3D/4D imagery annotations, outcomes annotations, costs annotations, resource consumption/utilization annotations, haptic annotations, to streaming imagery data, together with relevant imagery metadata, including appended imagery metadata and semantic metadata and annotations. Furthermore, each participant cognitive collaborant client can also use the TIMS Clini-Pod Network System to chat with each other during a collaboration session using a text chat facility. A separate text window box is displayed that allows for each participant cognitive collaborant to instant message each other in text format and include those images as input illustrations, as depicted in
The invention also works with wearable signals, sensors, devices and monitors—, collectively “mobile computing”, also known as Personal Digital Assistants. Participants (PDA) clients can use these PDAs to view, consult and collaborate on DICOM images. Personal digital assistant is any small mobile hand held device that provides computing and information storage such as hand held computers, phones, media display devices and handheld computers, including watches and vison.
The invention enables both synchronous and asynchronous multimodal cognitive communications, collaboration, consultation and instruction between and among participant cognitive collaborants, including heterogeneous networked teams of persons, machines, devices, neural networks, robots and algorithms. And specifically, the invention enables multimodal cognitive communications, collaboration, consultation and instruction during various stages of medical disease management, including detection, diagnosis, prognosis, treatment, measurement, monitoring and reporting.
In one embodiment the invention provides for a unique streamer-splitter-server-router functional combination in a single network edge device, a neurosynaptic network node, having bi-directional communications capability with other Pod network gateway servers via network, video and wireless connectivity. Network gateway servers—neurosynaptic network nodes—can be combined in various multichannel multiplexed combinations, including pod pairs (2), pod quads (4), pod squads (16), and pod hive clusters (64), as depicted in
In another embodiment the invention provides a method for recursive cognitive enrichment and collaborative knowledge exchange between and among cognitive collaborants, including heterogeneous networked teams of persons, machines, devices, neural networks, robots and algorithms. Specifically it provides neurosynaptic network connectivity enabling both synchronous and asynchronous multimodal cognitive communications, collaboration, consultation, instruction, that includes viewing, curating, annotating and tagging, using one or more sources of multichannel, multiplexed heterogeneous streaming imagery data, including both medical and non-medical streaming imagery data.
This embodiment also provides a method for rapid, adaptive deep learning and multisensory skills acquisition by and among cognitive collaborants, including heterogeneous networked teams of persons, machines, devices, neural networks robots and algorithms, with neurosynaptic network connectivity enabling both synchronous and asynchronous multimodal cognitive communications, collaboration, consultation, instruction, that includes viewing, curating, annotating and tagging, using one or more sources of multichannel, multiplexed heterogeneous streaming imagery data, including both medical and non-medical streaming imagery data, together with images, video, modality imagery, waveforms, audio and haptic files, multiomic—phenotypic, genomic, metabolomic, pathomic, radiomic, radiopathomic and radiogenomic—maps and clinical data sets, biometric maps and movies, hapmaps, heat maps, data stream visualizations, structured reports, and clinical documents during various stages of medical disease management, including detection, diagnosis, prognosis, treatment, measurement, monitoring and reporting.
A medical imagery stream is defined as a collection of one or more sources of streaming imagery data which comprise at least one image frame that defines a time progression of output from a video source. TIMS Clini-Docks maintain image quality from source modalities as required for conformance to DICOM Standards for clinical use. TIMS Clini-Docks specify streamer components that have secured regulatory clearances for transmission and viewing of medical imagery streams for clinical diagnostic purposes.
In one embodiment, TIMS Clini-Pod Network Servers (CNS) provide live video and audio communications, as well as a method of recording, transmitting and saving images in single file format structures, including those as specified in the DICOM Standard. DICOM is a medical imaging standard common in the medical industry. DICOM can also be defined as a standard in the field of medical informatics for exchanging digital information between medical imaging equipment (such as radiological imaging) and ensuring interoperability with other systems. DICOM, including protocols for device communication over a network, syntax and semantics for commands and associated information that can be exchanged using protocols, a set of storage services and devices claiming conformation to the standard, as well as file format and medical directory structures to facilitate access to images and related information stored on media that shares information. The embodiment can serve as the connection point between any medical imaging modality and a hospital PACS, medical archive or other image repository, including clinical data repositories, personalized clinical knowledge repositories, clinical cognitive vismeme vaults and metadata repositories.
One component of this invention, TIMS Clini-Pod Network Servers (CNS), are able to connect DICOM equipment and older non-DICOM equipment to a hospital network, allowing imaging studies to be stored and saved. The TIMS Clini-Pod Network System, this invention described herein, briefly described as a trace overlay and annotation system that users can collaborate with each other live, each viewing each other's object inputs and those object inputs can be encapsulated and saved in single file format structures, including those as specified in the DICOM Standard, in PACS, in a DICOM compliant image archives, or in other image repositories.
Another embodiment the TIMS Clini-Pod CNS network system can be deployed as to collaboration portals for multi-party clinical collaboration among specialist providers; care coordination for caregiving teams both local and remote; and patient provider engagement, the support of meaningful use goals and objectives for electronic medical records. Clini-Pod CNS also support health information exchange for integrated delivery systems; for biomedical, clinical and genomic mapping and multisensory data stream visualizations, as well as clinical decision support for value care-giving teams.
Still other embodiments provide networked informatics connectivity for medical kiosks, offices and retail clinics, ambulatory care and nursing facilities. Often these facilities have limited connectivity for access to hospital-based electronic medical systems. In those circumstances the TIMS Clini-Pod CNS as “LAND” [Local Adapter for Network Distribution] and “SEE” [Surrogate Electronic Health Record Environment] to facilitate health information exchange with hospitals and other caregiving facilities. Use of TIMS Clini-Pod access and enable groups with access to EHR systems to share electronic medical information with those who do not, and specifically by health information exchange with Consolidated Clinical Document Architecture (C-CDA″) compliant documents, including Continuity of Care Documents (CCD, CCD+, etc.), Fast Healthcare Interoperability Resources (“FHIR”) and Universal Transfer Forms (UTF.)
Other objects, features, and advantages will occur to those skilled in the art from the following description of an embodiment and the accompanying drawings, in which:
A network system 1 for allowing users to concurrently communicate live; concurrently collaborate live, concurrently consult live, and concurrently instruct live while concurrently viewing multiple sources of streaming imagery data 13 on a display screen using sketched and annotated participant cognitive collaborant input illustrations over streaming imagery data 13 among a group of remotely located participant cognitive collaborants 10, including heterogeneous networked teams of persons, machines, devices, neural networks, robots and algorithms.
The network system having at least one or more TIMS Clini-Pod Network Servers (CNS) 2 including associated data bases in communication with local area networks 3, in some circumstances connected to and having access to a medical PACS server 4 including associated database all capable of using the protocols required by the DICOM Standard and all having access to DICOM modality work list utilities for appending imagery metadata 5 including associated databases providing medical patient metadata, as well as imagery metatdata, semantic metadata and annotations, and archived annotated imagery. To collect streaming imagery data 13 the system together with at least one TIMS Clini-Dock 6 in contact with the local area network 3 wherein the TIMS Clini-Dock 6 is providing live streaming imagery data to the local area network 3 as it receives concurrent sources of live streaming imagery data 6 from multiple medical modalities 7,8,9 such as, but not limited to, ultrasound, fluoroscopy and video. A participant cognitive collaborant can view streaming imagery data 13 in single file format structures, including those as specified in the DICOM Standard together with participant cognitive collaborant input illustrations 18 which include, telestrations 21, drawings 22 and annotations 234 (known herein as input illustrations from participant cognitive collaborants) over the streaming imagery data and saving that streaming imagery data, relevant imagery metadata, including appended imagery metadata and semantic metadata and annotations, together with input illustrations from participant cognitive collaborants 18 in single file format structures, including those as specified in the DICOM Standard, locally in media libraries or image data repositories on their respective computer storage devices, in image data repositories on TIMS Clini-Pod Network Servers (CNS) 2, in image data repositories on cloud storage devices and locations, in image data repositories on picture archiving and communications systems PACS 4 or in other image data repositories compliant with standards for digital imaging and communications in medicine, or in any other data repository that allows streaming imagery data, annotations and metadata, including semantic metadata and annotations, to be combined in native single file format structures, including clinical data repositories, personalized clinical knowledge repositories, clinical cognitive vismeme vaults and metadata repositories.
This invention allows for one or more TIMS Clini-Ports 10 to concurrently use the network system at the same time. The network system 1 also allows participant cognitive collaborants to concurrently collaborate live, as defined by this system. The plurality of TIMS Clini-Ports can concurrently view multiple sources of live and archived streaming imagery data 13, and concurrently create input illustrations 18 over that streaming imagery data 13 which include telestrations 21, drawings 22 and annotations 23, as they are appended to that imagery, and encapsulate and save those participant cognitive collaborant input illustrations, including telestrations, drawings, and annotations, together with streaming imagery data, and relevant imagery metadata, including appended imagery metadata, from the collaboration session in single file format structures, known as collaborated imagery files. The network system 1 ‘single file encapsulate and save’ functionality encapsulates and saves collaborated imagery files in single file format structures, as may be required or allowed by standards for clinical documentation or medical records storage, including those as specified in the DICOM Standard, Clini-Pod Network locally in media libraries or image data repositories on their respective computer storage devices, in image data repositories on TIMS Clini-Pod Network Servers (CNS) 2, in image data repositories on cloud storage devices and locations, in image data repositories on picture archiving and communications systems PACS 4 or in other image data repositories compliant with standards for digital imaging and communications in medicine, or in any other data repository that allows streaming imagery data, annotations and metadata, including semantic metadata and annotations, to be combined in native single file format structures, including clinical data repositories, personalized clinical knowledge repositories, clinical cognitive vismeme vaults and metadata repositories.
TIMS Clini-Ports can retrieve archived collaborated imagery files for use during current or future collaboration sessions. TIMS Clini-Ports can include collaborated imagery files in patient studies. In one embodiment, a collaboration session can include one or more participant cognitive collaborants that can utilize personal digital assistants (PDA) over the internet 12.
A method for allowing one or more participant cognitive collaborants to concurrently collaborate live on medical images 13, all participants clients running substantially the same TIMS Clini-Port software application programs on each of the participant cognitive collaborant's computers; storing the programs on each of the participant cognitive collaborant's computers. Each participant cognitive collaborant computer displaying the graphic user interface output 25 of those programs on their computer display. Each participant cognitive collaborant computer linking to each other and to TIMS Clini-Pod Network Servers (CNS) 2 using local area networks 3. All TIMS Clini-Ports 10 have access to local area networks 3 and internet 12. TIMS Clini-Pod Network Servers (CNS) 2 providing authentication and authorization to each participant cognitive collaborant wherein linking the participant cognitive collaborant to DICOM Modality Worklist utilities 5, to image data repositories connected to picture archiving and communications systems via PACS servers 4, to other image data repositories compliant with standards for digital imaging and communications in medicine DICOM, to image data repositories connected via internet 12 to cloud storage devices and locations or on any other repository that allows streaming imagery data, annotations and metadata, including semantic metadata and annotations, to be combined in native single file format structures for viewing medical images 13, including clinical data repositories, personalized clinical knowledge repositories, clinical cognitive vismeme vaults and metadata repositories.
Streaming imagery data into local area networks 3 wherein TIMS Clini-Docks 6 are connected directly to medical modalities 7,8,9 acquiring live streaming imagery data or archived streaming imagery data, streaming that imagery data to TIMS Clini-Ports 10 via local area networks 3. TIMS Clini-Ports 10 acquire lists 15 of available medical modalities 7,8,9 from a local area network 3. Included in this network is are TIMS Clini-Pod Network Servers (CNS) 2 having associated databases, identifying each participant cognitive collaborant and the streaming imagery data available to each participant cognitive collaborant; identifying each participant cognitive collaborant the streaming imagery data that is available on each participant cognitive collaborant's computer. Also, local area networks 3 can be connected to the internet 12.
When a participant cognitive collaborant wants to view medical imagery and collaborate on that streaming imagery data with others, that participant cognitive collaborant selects a channel on the multi-channel source selection tab for viewing streaming imagery data 15, 25 so he/she can initiate a collaboration session, as depicted in
TIMS Clini-Pod Network Servers (CNS) 2 with dynamic signal synchronization ensures that the same imagery refresh rate is concurrently available on all participant cognitive collaborant computers. TIMS Clini-Pod Network Servers (CNS) 2 use a process of local registration to identify the image frames needed for viewing on each of the participant cognitive collaborant computers, and send to each of them only the image frames necessary for participation in a collaboration session. TIMS Clini-Pod Network Servers (CNS) 2 enables each participant cognitive collaborant 10 to use a scalable window so all input illustrations 18 for each and every participant cognitive collaborant 10 are dynamically ratio metric based on the underlying image aspect ratio of the respective computer of each participant cognitive collaborant 10. Each participant cognitive collaborant 10 views what every other authorized participant cognitive collaborant 10 views in that session.
TIMS Clini-Pod Network Servers (CNS) 2 distribute copies of streaming imagery data selected for use during a collaboration session to each of the participant cognitive collaborants. Since participant cognitive collaborants 10 collaborate only with copies of images, they do not alter the original streaming imagery data in any way. TIMS Clini-Pod Network Servers (CNS) 2 with dynamic signal synchronization allows at least one participant cognitive collaborant 10 to telestrate 21, draw 22, annotate 23, input illustrations 18 over the streaming imagery data 13 in a concurrently collaboration session wherein a participant cognitive collaborant 10 is telestrating 21, drawing 22, annotating 23 input illustrations 18 over the streaming imagery data 13. This approach of generating input illustrations 18 on TIMS Clini-Pod Network Servers (CNS) 2, and distributing only those input illustrations 18, and not the underlying images to each participant cognitive collaborant 10, significantly improves operating performance and reduces image latency and wait times.
TIMS Clini-Pod Network Servers (CNS) 2 manage input illustrations 18 from all participant cognitive collaborants 10 in a concurrently collaborative environment with image streams which can include multiple streams of streaming imagery data. TIMS Clini-Pod Network Servers (CNS) 2 manage participant cognitive collaborant 10 input illustrations 18, which include telestrations 21, drawings 22, and annotations 23 as they are appended to that imagery 13, and encapsulate and save those participant cognitive collaborant input illustrations 18, which include telestrations 21, drawings 22 and annotations 23 together with streaming imagery data 13, and relevant imagery metadata, including appended imagery metadata, from the collaboration session in single file format structures, known as collaborated imagery files.
TIMS Clini-Pod Network Servers (CNS) 2 ‘single file encapsulate and save’ functionality encapsulates and saves collaborated imagery files in single file format structures, as may be required or allowed by standards for clinical documentation or medical records storage, including those as specified in the DICOM Standard. Users can encapsulate and save collaborated imagery files locally in media libraries or image data repositories on their respective computer storage devices, as depicted in
TIMS Clini-Pod Network Servers (CNS) 2 create session logs that include collaboration session identification, participant cognitive collaborant information, information about streaming imagery data, including associated patient metadata, along with session dates and times, as shown in
In one embodiment, several participant cognitive collaborants 10, also known as Radiologist, Pathologist and Oncology Surgeon, utilize the network system 1 to collaborate in the provision of oncology care.
At Time 1, Radiologist retrieves patient's archived medical imagery from a PACS 4 image repository. Radiologist detects a suspicious nodule on several images and inputs telestrations 21 and drawings 22 indicating the location of the nodule, along with text annotations 23 charactering its clinical significance and voice annotations 23 summarizing his findings. Radiologist utilizes the ‘single file encapsulate and save’ functionality of the network system 1 to incorporate those input illustrations 18, together with medical imagery data 13 and identifying patient metadata, in single file format structures, known as a collaborated imagery file (CIF #1). Radiologist archives the CIF #1, which has been encapsulated and saved in a single file format compliant with the DICOM Standard, and sends to PACS 4 for review and discussion with other members of the oncology care team.
At Time 2, Radiologist invites Pathologist to a collaboration session to discuss his findings of a suspicious nodule as described in CIF #1. While both participant cognitive collaborants 10 are concurrently viewing CIF #1, Radiologist retrieves several additional collaborated imagery files from his local media library, and from PACS 4, of relevant prior patient medical imagery for display and viewing during the collaboration session, as shown in
At Time 3, Oncology Surgeon reviews CIS#1 and selects CIF #4 to create a surgical roadmap to guide tumor excision using input illustrations 18, which include telestrations 21, drawings 22, and voice annotations 23. Oncology Surgeon saves surgical roadmap as CIF #5.
At Time 4, Oncology Surgeon retrieves surgical roadmap (CIF #5), for intra-operative guidance during tumor removal.
At Time 5, during surgery, Oncology Surgeon invites Radiologist and Pathologist for intra-operative consultation during tumor excision.
At Time 6, participant cognitive collaborants—Oncology Surgeon, Radiologist, and Pathologist—utilize network system 1 to retrieve and concurrently view nodule (CIF #1), tumor pathology images (CIF #2, #3, #4), and surgical roadmap (CIF #5) from PACS 4, along with live streaming imagery data from endoscope 13 used during tumor excision.
Periodically during the surgical procedure, at Times 7,8,9, Oncology Surgeon consults with Pathologist to confirm sufficiency of margins around excised tumor. Pathologist confirms sufficiency of margins with telestrations 21, drawings 22, and text annotations 23, over live endoscopy images, saving all those input illustrations 18, together with associated streaming imagery data 13 in single file format structure as CIF #6.
At Time 10, Oncology Surgeon retrieves CIF #6 from PACS 4, which contains Pathologist's input illustrations 18 regarding excised tumor margins, and dictates a post-operative surgical report adding voice annotations 23, to telestrations 21, and drawings 22 to endoscopic images from excision surgery and saving in single file format structure as CIF #7.
At Time 11, Oncology Surgeon combines pre-operative surgical roadmap CIF #5 with post-operative surgical report CIF #7, along with pre-operative image study CIS #1 (which includes CIF #1, #2, #3, #4) into comprehensive clinical report (CIS #2) for distribution to the oncology care team.
Oncology Surgeon can encapsulate and save CIS #2 in single file format structures as specified in the DICOM Standard and send to PACS 4. Oncology Surgeon utilizes the ‘single file encapsulate and save’ functionality of the network system to encapsulate and save CIS #2 in single file format structures as specified in the DICOM Standard and send to PACS 4. Oncology Surgeon can also encapsulate and save CIS #2 in single file format structures as may be required or allowed for clinical documents, for storage in patient's electronic medical record, or for patient billing.
At Time 12, Oncology Surgeon retrieves CIS #2 from PACS 4, utilizes the network system 1 to remove all relevant identifying patient metadata, and encapsulates and saves as an anonymized collaborated imagery study (CIS #3) for use as teaching files with surgical fellows.
In another embodiment, a participant cognitive collaborant 10, known as Hospitalist, remotely monitors live streaming imagery data 13 from a surgical procedure in an operating room on channel one, and archived streaming imagery data 13 of a patient recovering in Intensive Care Unit, on channel two. While monitoring streaming imagery data 13 on channels one and two, as depicted in
In another embodiment, a patient is recalled to undergo a second PET/MRI scan. The previous test yielded inconclusive, due to patient motion during image capture, thus requiring a costly retest. During the second test, Radiologist was able to review the MRI images captured 13 during the first portion of the test, while the patient was still being imaged in PET unit and confirm that the second MRI scan was useable. Radiologist was able to advise Attending Molecular Pathologist during PET scan 13 of additional regions of interest with input illustrations 18 for further investigation.
In another embodiment, Oncologist wishes to convene a virtual tumor board for the following day involving multi-specialist collaboration with a patient's Radiologist, Pathologist, Oncology Surgeon and himself Oncologist sends invitations to colleagues along with several collaborated imagery files he wishes to review during the collaboration session. Radiologist and Pathologist confirm availability, but Oncology Surgeon is unable to attend. However, Oncology Surgeon is able to annotate 23 with telestrations 21 and drawings 22 on several key images 13 included in the collaborated imagery study sent with the session invitation. Oncology Surgeon also includes his clinical notes and an audio file along with his report, together all encapsulated as a CIF and returned to the session host.
During the collaboration session the following day, the host Oncologist retrieves patient images from PACS 4 and from his local media library 25 containing the CIF 13, 18 sent to him from Oncology Surgeon, viewing both images concurrently when colleagues from radiology and pathology join the collaboration session. During the collaboration session, Pathologist is monitoring on the third channel of the multi-channel streamer 7,8,9, 25, a tumor removal of another patient in the operating room, advising that Oncology Surgeon intra-operatively regarding sufficiency of margins of tumor removal from that patient. Oncology Surgeon is able to share live imagery 13 of the tumor removal with the radiology and oncology colleagues who have joined the virtual tumor board collaboration session.
At the conclusion of the collaboration session, host Oncologist encapsulates and saves input illustrations 18 from participant cognitive collaborants 10, including encapsulated audio clinical notes and biopsy reports as clinical documents, saving them as collaborated imagery files and sending them to all participant cognitive collaborants 10 as well as invitees unable to attend. Additionally, the CIFs 13, 18 are sent to PACS 4 for inclusion in the patient's electronic medical records as well to patient's referring clinician.
Other embodiments of the invention include applications for cognitive enterprise imaging with streaming imagery informatics, as depicted in
The principle preferred embodiments and modes of operation of the present invention have been described in the forgoing specification. The invention which is intended to be protected herein, however, is not to be construed as limited to the particular embodiments disclosed, since these embodiments are to be regarded as illustrative rather than restrictive. Variations and changes may be made by others without departing from the spirit of this invention. Accordingly, it is expressly intended that all such variation and changes which fall within the spirit and scope of the claims be embraced thereby.
This application is Continuation-in-part of U.S. application Ser. No. 13/999,688 filed Mar. 15, 2014 entitled:
